Is .data still useful in pytorch?
Question:
I’m new to pytorch. I read much pytorch code which heavily uses tensor’s .data member. But I search .data in the official document and Google, finding little. I guess .data contains the data in the tensor, but I don’t know when we need it and when not?
Answers:
.data was an attribute of Variable (object representing Tensor with history tracking e.g. for automatic update), not Tensor. Actually, .data was giving access to the Variable‘s underlying Tensor.
However, since PyTorch version 0.4.0, Variable and Tensor have been merged (into an updated Tensor structure), so .data disappeared along the previous Variable object (well Variable is still there for backward-compatibility, but is deprecated).
Paragraph from Release Notes for version 0.4.0 (I recommend reading the whole section about Variable/Tensor updates):
What about .data?
.data was the primary way to get the underlying Tensor from a
Variable. After this merge, calling y = x.data still has similar
semantics. So y will be a Tensor that shares the same data with
x, is unrelated with the computation history of x, and has
requires_grad=False.
However, .data can be unsafe in some cases. Any changes on x.data
wouldn’t be tracked by autograd, and the computed gradients would be
incorrect if x is needed in a backward pass. A safer alternative is
to use x.detach(), which also returns a Tensor that shares data
with requires_grad=False, but will have its in-place changes
reported by autograd if x is needed in backward.
Aside from @benjaminplanche ‘s answer, I’d use it to manually change values of parameters.
For instance, I have the following model:
model = nn.Sequential(nn.Linear(10, 1))
and for some reason, I’d like to manually update the values of its parameters. Then, I can do:
for param in model.parameters():
param.data = 10 * param.data # multiply the parameter values by 10.
Note that if we remove .data behind param, the parameter values won’t be updated.
Such use can be found in BYOL (Bootstrap your own latent) and this Github webpage for BYOL pytorch implementation.
From PyTorch 0.4.0 and at least version 1.7.1 – you can take torch.Tensor content via this attributed ".data".
Assume you have point=torch.Tensor(size=(1,2,)); point.requires_grad_(True);
In that case:
point.data will be a Tensor that shares the same data with point.
You can check it with: point.data_ptr(); point.data.data_ptr();
-
it’s is unrelated to the computation history of point.data, has requires_grad=False even point has requires_grad=True
-
Any changes on initial_point.data wouldn’t be tracked by autograd
Documentation:
I’m new to pytorch. I read much pytorch code which heavily uses tensor’s .data member. But I search .data in the official document and Google, finding little. I guess .data contains the data in the tensor, but I don’t know when we need it and when not?
.data was an attribute of Variable (object representing Tensor with history tracking e.g. for automatic update), not Tensor. Actually, .data was giving access to the Variable‘s underlying Tensor.
However, since PyTorch version 0.4.0, Variable and Tensor have been merged (into an updated Tensor structure), so .data disappeared along the previous Variable object (well Variable is still there for backward-compatibility, but is deprecated).
Paragraph from Release Notes for version 0.4.0 (I recommend reading the whole section about Variable/Tensor updates):
What about
.data?
.datawas the primary way to get the underlyingTensorfrom a
Variable. After this merge, callingy = x.datastill has similar
semantics. Soywill be aTensorthat shares the same data with
x, is unrelated with the computation history ofx, and has
requires_grad=False.However,
.datacan be unsafe in some cases. Any changes onx.data
wouldn’t be tracked byautograd, and the computed gradients would be
incorrect ifxis needed in a backward pass. A safer alternative is
to usex.detach(), which also returns aTensorthat shares data
withrequires_grad=False, but will have its in-place changes
reported byautogradifxis needed in backward.
Aside from @benjaminplanche ‘s answer, I’d use it to manually change values of parameters.
For instance, I have the following model:
model = nn.Sequential(nn.Linear(10, 1))
and for some reason, I’d like to manually update the values of its parameters. Then, I can do:
for param in model.parameters():
param.data = 10 * param.data # multiply the parameter values by 10.
Note that if we remove .data behind param, the parameter values won’t be updated.
Such use can be found in BYOL (Bootstrap your own latent) and this Github webpage for BYOL pytorch implementation.
From PyTorch 0.4.0 and at least version 1.7.1 – you can take torch.Tensor content via this attributed ".data".
Assume you have point=torch.Tensor(size=(1,2,)); point.requires_grad_(True);
In that case:
point.datawill be a Tensor that shares the same data withpoint.
You can check it with: point.data_ptr(); point.data.data_ptr();
-
it’s is unrelated to the computation history of
point.data, hasrequires_grad=Falseevenpointhasrequires_grad=True -
Any changes on initial_point.data wouldn’t be tracked by autograd
Documentation: